- Home
- Skills
- Agents & Orchestration
- incremental implementation
incremental implementation
Enforce execution discipline by implementing features in small, tested, and verifiable vertical slices.
Free
Works with the AI Agents you already use
incremental implementation
Example session with this skill installed
Implement the user profile update feature using vertical slices. Start with the database schema and the API endpoint only.
- Read your context and instructions
- Compiled the incremental implementation
I will implement the profile update feature incrementally, starting with the backend slice.
Increment 1: Database and API
I have updated the Prisma schema and implemented the PATCH endpoint. I verified the change by running the test suite and confirmed the database migration is revertible.
| Action | Status | Command/Result |
|---|---|---|
| Schema Update | Success | Added bio and avatarUrl to User model |
| Migration | Verified | npx prisma migrate dev successful |
| API Logic | Success | Implemented PATCH /api/users/profile |
| Verification | Passed | npm test src/api/users (4 tests passed) |
| Build Check | Passed | npx tsc --noEmit successful |
Simplicity Check:
- No new utility classes created; used existing
dbclient. - No changes to authentication middleware (out of scope).
- Validation uses the existing Zod schema.
Next steps
- Implement the frontend form component in the next slice.
- Connect the form to the API endpoint.
- Add success/error toast notifications.
Connects securely to your tools. The creator never sees your data.
About this skill
Large pull requests are where bugs hide and reviews go to die. When an agent attempts to implement a complex feature in a single massive wall of code, it inevitably breaks existing functionality or misses edge cases. This skill enforces execution discipline by breaking down multi-file changes into thin, vertical slices that maintain a working system at every step.
What it does
- Vertical slicing ensures each increment delivers end-to-end functionality across DB, API, and UI.
- Scope discipline prevents "while I'm here" refactoring and unnecessary changes to adjacent files.
- Simplicity enforcement rejects premature abstractions and complex patterns in favor of naive, correct code.
- Continuous verification mandates running build and test commands after every logical change.
- Risk mitigation prioritizes high-uncertainty components first to fail fast.
How it works
- Slice the task into the smallest complete pieces of functionality that leave the system in a testable state.
- Implement the first slice using the simplest possible logic, avoiding any unrelated code cleanup.
- Verify the change by running the repository's test suite, build commands, and type checkers.
- Commit the verified slice with a descriptive message before moving to the next requirement.
Frameworks & tools
This skill is language-agnostic and works with any stack including Node.js, Python, Java, and Go. It integrates with standard development workflows using Git, CI/CD pipelines, and feature flagging systems.
Why this beats prompting it yourself
Generic prompts often lead agents to over-engineer solutions or produce massive diffs that are impossible to debug. This skill embeds strict rules against scope creep and premature abstraction, forcing the agent to prove correctness through code execution rather than just text generation.
Use cases
- Feature development from a complex task breakdown or technical specification.
- Refactoring legacy codebases where changes must be isolated to prevent regression.
- Parallel development using contract-first slicing for backend and frontend sync.
- Risk management for proof-of-concept work involving unstable third-party APIs or WebSockets.
Known limitations
Not recommended for single-file, single-function changes where the scope is already minimal. It requires an existing test or build command to provide meaningful verification.
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean 2 days ago
- Free to download with an account
Requires